index.c File Reference

File index mapping and serialization implementation. More...

#include "index.h"
#include <errno.h>
#include <inttypes.h>
#include <stdlib.h>
#include <string.h>
#include "jemalloc/jemalloc.h"
#include "je.h"
#include "log.h"

Include dependency graph for index.c:

Macros
#define	indexbucket(hash)   ((int) (hash & INDEXBUCKETSMASK))
	Maps and casts the hash value to a bucket index via the last N bits (where N is the number of buckets, INDEXBUCKETS).
#define	INDEXWRITEFMT   "%s,%" PRIu64 ",%" PRIu64 ",%" PRIu64 "\n"
	Format string used for writing index entries to a file stream.

Typedefs
typedef int(*	indexwriter_fn) (void *ctx, const char *buf, int len)
	Function pointer type for writing a buffer to a stream.

Functions
uint64_t	indexhash (const char *fp)
	Hashes the filepath string for use in the index map.
struct inode_s *	indexfind (const struct index_s *idx, const char *fp, const uint64_t fphash)
	Searches the index for a node with a matching filepath.
static int	indexnodecmp (const void *a, const void *b)
	Compares two file nodes for sorting in ascending order by filepath.
static int	indexwriter_file (void *ctx, const char *buf, const int len)
static int	indexwriter_gz (void *ctx, const char *buf, const int len)
static int	indexwrite_impl (struct index_s *idx, void *ctx, indexwriter_fn wfn)
	Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the stream context and freed.
int	indexwrite (struct index_s *idx, FILE *s)
	Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the file stream and freed.
int	indexwrite_gz (struct index_s *idx, gzFile gz)
	Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the gzip stream and freed.
int	indexread (struct index_s *idx, gzFile gz)
	Reads a gzip file stream and deserializes the contents into a map of individual file nodes. Transparently handles both compressed and uncompressed input.
static void	indexappend (struct ibucket_s *bucket, struct inode_s *node)
	Appends the node to the end of the bucket (linked list), potentially assigning a new head if the bucket is empty.
struct inode_s *	indexput (struct index_s *idx, const char *fp, const uint64_t fphash, const struct fsstat_s *st, const uint64_t xx)
	Copies the node and inserts it into the index mapping.
static void	indexfree_r (struct inode_s *idx)
	Recursively frees a linked list of nodes starting from a given head.
void	indexfree (struct index_s *idx)
	Frees all nodes in the index map.
struct inode_s **	indexlist (const struct index_s *idx)
	Flattens the index map into an unsorted array of nodes. The list is dynamically allocated and must be freed by the caller. Array size is determined by the size field in the index struct.

Variables
static char	indexfpbuf [1024]
	Filepath buffer for index I/O operations.

Detailed Description

File index mapping and serialization implementation.

Macro Definition Documentation

indexbucket

#define indexbucket

(

hash

)

((int) (hash & INDEXBUCKETSMASK))

Maps and casts the hash value to a bucket index via the last N bits (where N is the number of buckets, INDEXBUCKETS).

INDEXWRITEFMT

#define INDEXWRITEFMT   "%s,%" PRIu64 ",%" PRIu64 ",%" PRIu64 "\n"

Format string used for writing index entries to a file stream.

Typedef Documentation

indexwriter_fn

typedef int(* indexwriter_fn) (void *ctx, const char *buf, int len)

Function pointer type for writing a buffer to a stream.

Parameters

ctx	The stream context (FILE* or gzFile)
buf	The buffer to write
len	The length of the buffer

Returns

0 on success, -1 on error.

Function Documentation

indexappend()

static void indexappend ( struct ibucket_s *  bucket, struct inode_s *  node  )

static

Appends the node to the end of the bucket (linked list), potentially assigning a new head if the bucket is empty.

Parameters

head	The head of the linked list
node	The node pointer to insert

Here is the caller graph for this function:

indexfind()

struct inode_s * indexfind	(	const struct index_s *	idx,
		const char *	fp,
		uint64_t	fphash
	)

Searches the index for a node with a matching filepath.

Parameters

idx	The index to search
fp	The search value (filepath) to compare
fphash	The hash value of the filepath to compare

Returns

If a match is found, its pointer is returned, otherwise NULL.

Here is the caller graph for this function:

indexfree()

void indexfree

(

struct index_s *

idx

)

Frees all nodes in the index map.

Parameters

idx	The index to free

Here is the call graph for this function:

Here is the caller graph for this function:

indexfree_r()

static void indexfree_r ( struct inode_s *  idx )

static

Recursively frees a linked list of nodes starting from a given head.

Parameters

idx	The head of the linked list

Here is the caller graph for this function:

indexhash()

uint64_t indexhash

(

const char *

fp

)

Hashes the filepath string for use in the index map.

Note

64-bit FNV-1a implementation is used for hashing.

Parameters

fp	The filepath string to hash

Returns

The hashed value of the filepath.

Here is the caller graph for this function:

indexlist()

struct inode_s ** indexlist

(

const struct index_s *

idx

)

Flattens the index map into an unsorted array of nodes. The list is dynamically allocated and must be freed by the caller. Array size is determined by the size field in the index struct.

Parameters

idx	The index to flatten

Returns

If successful, a pointer to an array of size idx->size is returned. Otherwise, NULL is returned and errno is set.

Here is the caller graph for this function:

indexnodecmp()

static int indexnodecmp ( const void *  a, const void *  b  )

static

Compares two file nodes for sorting in ascending order by filepath.

Parameters

a	The first file node to compare
b	The second file node to compare

Returns

The result of the comparison.

Note

This function is equivalent to strcmp(a->fp, b->fp).

Here is the caller graph for this function:

indexput()

struct inode_s * indexput	(	struct index_s *	idx,
		const char *	fp,
		uint64_t	fphash,
		const struct fsstat_s *	st,
		uint64_t	xx
	)

Copies the node and inserts it into the index mapping.

Parameters

idx	The index to insert into
fp	The file path to use for the new node, duplicated internally
fphash	The file path hash value to use for the new node
st	The file stat info to use for the new node
xx	The xxHash64 hash value to use for the new node

Returns

The pointer to the new node in the index map, otherwise NULL is returned and errno is set.

Here is the call graph for this function:

Here is the caller graph for this function:

indexread()

int indexread	(	struct index_s *	idx,
		gzFile	gz
	)

Reads a gzip file stream and deserializes the contents into a map of individual file nodes. Transparently handles both compressed and uncompressed input.

Parameters

idx	The index to populate
gz	The gzip file stream to read from

Returns

If successful, 0 is returned. Otherwise, -1 is returned and errno is set.

Here is the call graph for this function:

Here is the caller graph for this function:

indexwrite()

int indexwrite	(	struct index_s *	idx,
		FILE *	s
	)

Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the file stream and freed.

Parameters

idx	The index to flatten
s	The file stream to write to

Returns

If successful, 0 is returned. Otherwise, -1 is returned and errno is set.

Here is the call graph for this function:

Here is the caller graph for this function:

indexwrite_gz()

int indexwrite_gz	(	struct index_s *	idx,
		gzFile	gz
	)

Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the gzip stream and freed.

Parameters

idx	The index to flatten
gz	The gzip file stream to write to

Returns

If successful, 0 is returned. Otherwise, -1 is returned and errno is set.

Here is the call graph for this function:

Here is the caller graph for this function:

indexwrite_impl()

static int indexwrite_impl ( struct index_s *  idx, void *  ctx, indexwriter_fn  wfn  )

static

Flattens the index map into a sorted array of nodes (by filepath). The list is then written to the stream context and freed.

Parameters

idx	The index to flatten
ctx	The stream context (FILE* or gzFile)
wfn	The writer function to use for output

Returns

If successful, 0 is returned. Otherwise, -1 is returned.

Here is the call graph for this function:

Here is the caller graph for this function:

indexwriter_file()

static int indexwriter_file ( void *  ctx, const char *  buf, const int  len  )

static

Here is the caller graph for this function:

indexwriter_gz()

static int indexwriter_gz ( void *  ctx, const char *  buf, const int  len  )

static

Here is the caller graph for this function:

Variable Documentation

indexfpbuf

char indexfpbuf[1024]

static

Filepath buffer for index I/O operations.